OpenAI’s open-weight release

gpt-oss

Name: gpt-oss
Author: OpenAI

by OpenAI

Chat Tools

OpenAI’s open-weight gpt-oss models (20B and 120B) bring strong general reasoning and tool use under an Apache 2.0 licence.

Publisher: OpenAI
Context window: 128K tokens
Sizes: 20B, 120B
Licence: Apache 2.0

Model card on Hugging Face

Run gpt-oss

Install it on a Pendra worker, then call it through the OpenAI-compatible API with a pdr_sk_ key.

from pendra import Pendra

client = Pendra(api_key="pdr_sk_...")

response = client.chat.completions.create(
    model="gpt-oss:20b",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

import { Pendra } from "pendra";

const client = new Pendra({ apiKey: "pdr_sk_..." });

const response = await client.chat.completions.create({
  model: "gpt-oss:20b",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);

Run gpt-oss on your own UK infrastructure

Deploy a worker, install gpt-oss, and start serving it through one sovereign API endpoint.

Get started free Read the quickstart

Related models

Whisper

OpenAI